Zhu, XuanyingGedeon, TomCaldwell, SabrinaJones, Richard2024-01-21April 25-2978-172811213-8http://hdl.handle.net/1885/311663We can physically sense depression in others, and this recognition can be detected by using neural networks to analyse our physiological responses to observing individuals with depression. The behaviour of 16 individuals suffering from various levels depression were shown in short videos to 12 experiment participants (observers) whose physiological signals we recorded. Consciously, depression is not normally interesting, so does not provoke strong conscious recognition, and hence barely over chance, at 27%. However, at emotional levels, depression is interesting, so provokes physiological reactions we can measure, leading to neural network classification of 92%.application/pdfen-AU© 2019 IEEEDepression DetectionPhysiological SignalsGalvanic Skin ResponseSkin TemperaturePupil Dilation201910.1109/INES46365.2019.91095192022-10-02